Research map / Detection and segmentation / CNN features
Revisiting Face Forgery Detection: From Facial Representation to Forgery Detection
Zonghui Guo, Yingjie Liu, Jie Zhang, Haiyong Zheng, Shiguang Shan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add supervised ImageNet-1K pre-training | ViT-B · avg cross-set AUC | AUC (%): 61.12 -> 77.11 | Improved |
| use ViT-B instead of ResNet-50 with MoCo v3 | MoCo v3 · avg cross-set AUC | AUC (%): 78.24 -> 82.01 | Improved |
| replace supervised with BEiT v2 pre-training | ViT-B · avg cross-set AUC | AUC (%): 77.11 -> 82.70 | Improved |
| raise input resolution from 224 to 384 | ViT-B SL-1K · avg cross-set AUC | AUC (%): 77.11 -> 78.26 | Improved |
| increase network size within an architecture | ResNet SL-1K · avg cross-set AUC | AUC (%): 75.89 -> 76.61 | No clear effect |
| pre-train BEiT v2 on real-face data instead of ImageNet-1K | ViT-B · avg cross-set AUC | AUC (%): 82.70 -> 83.77 | Improved |
| further pre-train ImageNet BEiT v2 on real faces | FaceBEiT · avg cross-set AUC | AUC (%): 82.70 -> 86.56 | Improved |
| further pre-train MAE on real faces | FaceMAE · avg cross-set AUC | AUC (%): 79.22 -> 80.65 | Improved |
| add decorrelation loss L_dec (ablation) | CFB · avg cross-set AUC | AUC (%): 87.04 -> 88.14 | Improved |
| add uncertainty-based fusion module UFM (ablation) | CFB · avg cross-set AUC | AUC (%): 88.14 -> 88.64 | Improved |
| add evidential loss L_EDU (ablation) | CFB · avg cross-set AUC | AUC (%): 88.64 -> 88.78 | Improved |
| add L_EDU to FaceBEiT alone (ablation) | FB · avg cross-set AUC | AUC (%): 86.56 -> 87.43 | Improved |
Closest papers by meaning
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (CVPR 2025 · similarity 0.91)
- DF40: Toward Next-Generation Deepfake Detection (NeurIPS 2024 · similarity 0.91)
- DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces (NeurIPS 2025 · similarity 0.90)
- FakeDiffer: Distributional Disparity Learning on Differentiated Reconstruction for Face Forgery Detection (AAAI 2025 · similarity 0.89)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.89)
- Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
